中文版 | English

在结果中检索

CASIA OpenIR

浏览/检索结果: 共20条，第1-10条 帮助

限定条件                    
已选(0)清除 条数/页：   排序方式：
Improving Deep Neural Network Based Speech Synthesis through Contextual Feature Parametrization and Multi-Task Learning 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 1025-1037
作者:  Wen, Zhengqi;  Li, Kehuang;  Huang, Zhen;  Lee, Chin-Hui;  Tao, Jianhua;  Zhengqi Wen
收藏  |  浏览/下载：97/0  |  提交时间：2020/10/27
Dnn-based Speech Synthesis  Vocoder  Speech Parametrization  Blstm  Phoneme Embedded Vector  Multi-task Learning  Pitch-scaled Spectrum  
Investigating Deep Neural Network Adaptation for Generating Exclamatory and Interrogative Speech in Mandarin 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 1039-1052
作者:  Zheng, Yibin;  Li, Ya;  Wen, Zhengqi;  Liu, Bin;  Tao, Jianhua;  Jianhua Tao
收藏  |  浏览/下载：112/0  |  提交时间：2020/10/27
Speech Synthesis  Excitation Parameters  Deep Neural Network Adaptation  Exclamatory Speech  Interrogative Speech  
CTC Regularized Model Adaptation for Improving LSTM RNN Based Multi-Accent Mandarin Speech Recognition 期刊论文
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2018, 卷号: 90, 期号: 7, 页码: 985-997
作者:  Jiangyan Yi;  Zhengqi Wen;  Jianhua Tao;  Hao Ni;  Bin Liu
浏览  |  Adobe PDF(1416Kb)  |  收藏  |  浏览/下载：138/52  |  提交时间：2020/10/22
multi-accent, Mandarin speech recognition,LSTM-RNN-CTC, model adaptation, CTC regularization  
Deep Learning Based Speech Separation via NMF-style Reconstructions 期刊论文
IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, 2018, 卷号: 26, 期号: 11, 页码: 2043-2055
作者:  Shuai Nie;  Shan Liang;  Wenju Liu;  Xueliang Zhang;  Jianhua Tao
浏览  |  Adobe PDF(2922Kb)  |  收藏  |  浏览/下载：206/79  |  提交时间：2020/10/22
Speech separation  deep neural network (DNN)  nonnegative matrix factorization (NMF)  spectro-temporal structures  
Empirical ExploringWord-Character Relationship for Chinese Sentence Representation 期刊论文
ACM Transactions on Asian and Low-Resource Language Information Processing, 2018, 卷号: 3, 期号: 17, 页码: 1-15
作者:  shaonan wang;  jiajun zhang;  chengqing zong
浏览  |  Adobe PDF(2098Kb)  |  收藏  |  浏览/下载：85/35  |  提交时间：2020/10/13
Sentence representation  composition model  
Progressive Neural Networks based Features Prediction for the Target Cost in Unit-Selection Speech Synthesizer 会议论文
, 北京, 2018-8
作者:  Fu, Ruibo;  Tao, Jianhua;  Wen, Zhengqi
浏览  |  Adobe PDF(1188Kb)  |  收藏  |  浏览/下载：209/64  |  提交时间：2020/06/27
speech synthesis  progressive neural networks  unit-selection  target cost  
Transfer Learning based Progressive Neural Networks for Acoustic Modeling in Statistical Parametric Speech Synthesis 会议论文
, 印度海得拉巴, 2018-9
作者:  Fu, Ruibo;  Tao, Jianhua;  Zheng, Yibin;  Wen, Zhengqi
浏览  |  Adobe PDF(340Kb)  |  收藏  |  浏览/下载：243/50  |  提交时间：2020/06/27
Deep Metric Learning for the Target Cost in Unit-Selection Speech Synthesizer 会议论文
, 印度海得拉巴, 2018-9
作者:  Fu, Ruibo;  Tao, Jianhua;  Zheng, Yibin;  Wen, Zhengqi
浏览  |  Adobe PDF(323Kb)  |  收藏  |  浏览/下载：266/59  |  提交时间：2020/06/27
speech synthesis  unit-selection  target cost  deep metric learning  
基于静音时长和文本特征融合的韵律边界自动标注 期刊论文
清华大学学报（自然科学版）, 2018, 卷号: 58, 期号: 1, 页码: 61-66,74
作者:  傅睿博;  陶建华;  李雅;  温正棋
浏览  |  Adobe PDF(1160Kb)  |  收藏  |  浏览/下载：298/107  |  提交时间：2020/06/21
韵律边界标注  决策融合  静音时长  语料库构建  语音合成  
Boosting noise robustness of acoustic model via deep adversarial training 会议论文
, 加拿大卡尔加里, 2018-4-15
作者:  Liu, Bin;  Nie, Shuai;  Zhang, Yaping;  Ke, Dengfeng;  Liang, Shan;  Liu, Wenju
浏览  |  Adobe PDF(300Kb)  |  收藏  |  浏览/下载：200/85  |  提交时间：2020/05/15
Robust Speech Recognition  Deep Adversarial Training  Acoustic Model  Generative Adversarial Net